Heart Disease Prediction Framework Using Soft Voting-Based Ensemble Learning Techniques

Abstract

Cardiovascular disease is among the leading sources of the growing rate of morbidity and mortality worldwide, affecting roughly 50% of the adult age group in the healthcare sector. Heart disease claims the lives of about one person per minute in this modern era. Accurate detection methods for the timely identification of cardiovascular disorders are essential because there is rapid growth in the number of patients with this disease. The goal is to understand risk factors by analyzing the heart monitoring dataset using exploratory data analysis. This chapter proposes a heart disease prediction framework using soft voting-based ensemble learning techniques. Performance evaluation of the proposed framework and its comparison with the state-of-the-art models are done using a benchmark dataset in terms of accuracy, precision, sensitivity, specificity, and F1-score. Heart disease is a long-term problem with a greater risk of becoming worse over time. The proposed model has achieved an accuracy of 90.21%.